Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build or extend a course knowledge outline from class notes and textbooks in your format. Provides the scaffolding — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from [material]", or points to class materials.
Trigger: when the user agonizes over buying or selling because of stock price swings, judges by PE/K-line, or asks "should I take profit / cut losses". Language signals: "can it still go up", "should I take profit", "what if I'm stuck underwater", "this stock is cheap". Core shift: abstract a listed company as "an unlisted company with only one shareholder"; price swings = someone else's bid, not a change in company value. Not applicable to: pure information lookup, asset allocation discussions, short-term strategies, or clear speculation where the user won't shift perspective. Distinction: DCF answers "how much is it worth"; this skill answers "with what identity do you think"; opportunity-cost answers "buy or sell"; this skill answers "who are you".
Generate shareable paper summaries for Discord/Slack/Twitter. Use when user provides arxiv paper(s) and wants a digestible summary to share. Triggers on phrases like "논문 요약", "paper summary", "share this paper", "디스코드에 공유", "summarize for sharing". Produces insight-centered single-paragraph summaries that explain WHY research matters, not just WHAT it does.
Use when user wants to create a full slide deck or presentation using PaperBanana image generation, OR modify/regenerate an existing PaperBanana slide deck, OR build an editable PPTX with native text/tables/charts. Triggers on "make slides", "create presentation", "PPT", "slide deck", "regenerate slides", "update slides", "paperbanana slides", "editable PPTX", "editable slides". Also triggers when user has an existing slide-deck directory with outline.md and wants to regenerate images or make changes. This is the PRIMARY slide deck skill — always prefer over baoyu-slide-deck.
A skill that converts the tacit knowledge of existing features into specifications and generates an as-is Context Pack (a documentation folder organized by topic). Triggered by keywords "기능 문서화", "기존 기능 분석", "as-is 정리", "docs/기능별설명 생성". If you need a Spec for a new feature, use peach-gen-spec.
Coordinate installed skills and native subagents for bounded multi-stage outcomes, parallel work, context isolation, or independent judgment. Use when the user requests delegation or the desired outcome materially benefits from several owned results. Exclude single-skill routing, host setup, scheduling, and persistent agent runtimes.
Define and document performance budgets for a web service or application. Use when asked to set performance targets, define SLOs for latency or throughput, establish Core Web Vitals targets, create a performance baseline, or document performance regression policy. Produces a structured performance budget covering key user journeys, Core Web Vitals, backend latency SLOs, measurement tooling, CI enforcement, and breach response process.
Expert performance decisions for iOS/tvOS: when to optimize vs premature optimization, profiling tool selection, SwiftUI view identity trade-offs, and memory management strategies. Use when debugging performance issues, optimizing slow screens, or reducing memory usage. Trigger keywords: performance, Instruments, Time Profiler, Allocations, memory leak, view identity, lazy loading, @StateObject, retain cycle, image caching, faulting, batch operations
Execute wallet operations through the Phantom MCP server. Use when the user wants to interact with their Phantom wallet directly — get addresses, transfer SOL or SPL tokens, buy/swap tokens, sign transactions, and sign messages across Solana, Ethereum, Bitcoin, and Sui. Requires the @phantom/mcp-server to be configured as an MCP server.
Design conventions and visual quality guide for Phoenix projects using DuskMoon UI. Defines component color defaults, theme setup, surface elevation, color pairing rules, typography, layout composition, and motion patterns. Read this before writing any HEEX template, CSS, layout code, or creating new pages/views.
Generate a Personal Information Protection Impact Assessment (PIA) in an internal format for new features, products, or processing activities, using the structure learned from seed PIAs. Use when the user says "write a PIA," "personal information protection impact assessment," "do we need a PIA for this," "do a privacy review for this feature," or describes a new personal information processing activity.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
Use when writing, debugging, or reviewing Playwright tests for web apps; before writing test code; when tests are flaky, slow, or brittle; when seeing timeout errors, element not found, or race conditions; when using getByRole, locators, or assertions
PostgreSQL procedural language (PL/pgSQL). Covers stored procedures, functions, triggers, exception handling, and control structures. Use for PostgreSQL server-side programming. USE WHEN: user mentions "plpgsql", "PostgreSQL functions", "PostgreSQL procedures", "PostgreSQL triggers", "RETURNS TABLE", "RETURNS SETOF", "RAISE NOTICE" DO NOT USE FOR: basic PostgreSQL SQL - use `postgresql` instead, PL/SQL (Oracle) - use `plsql` instead, T-SQL - use `tsql` instead
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
Keep personal information processing rules aligned with practice. Two modes: a weekly scan of saved PIAs, DPA reviews, and triage results to find processing rule drift; or a direct query against proposed new practices. Use when the user asks "do our processing rules cover this," "we want to start doing X — do the processing rules need updating," "run the processing rule monitor," "processing rule scan," or wants to find where the processing rules no longer match what the team actually does.
Produce a proposed policy revision (marked-up version) that closes a gap. Triggered by a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. A first draft for internal review — not applied directly to the approved policy document. Use when the user says "rewrite the policy", "draft a policy fix", "mark up the policy", or gap-surfacer passes over a gap for drafting.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Professional product requirements document (PRD) writing assistant. Used to turn product requirements into clearly structured, complete PRD documents. **Use cases:** (1) writing requirements documents for new product features (2) requirements documents for optimizing existing features (3) turning user stories into PRDs (4) quickly generating a PRD draft. **Trigger words:** "写PRD", "生成PRD", "产品需求文档", "PRD文档"
Write product requirements documents (PRD) and generate interactive prototypes. Triggered when the user mentions "需求文档", "PRD", "产品需求", "写需求", "原型", "feature list" and similar keywords. Integrates the UI-UX-Pro-Max design system and supports Cloudflare Pages deployment.
Create distinctive, production-grade frontend interfaces with high design quality using the primer design system and brand guidelines. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates polished code and UI design that fully conforms to the primer design system.
Make a YC-grade product demo video (45–60s) from the real app code in a repo, with a script, animated composition, frame-perfect recording, captions, an AI voiceover plan, self-scoring sound design, and music mixing. Use when the user asks to make a product demo, a demo video for an app, a launch video, a promo video from their code, to record an app for a demo, add sound to a demo, fix stutter in a screen recording, or add captions, voiceover, sound effects, or music to a product video. Part of Showreel; reference outputs are the Vouch and Excalidraw demos.
Research and validate product names with competitor analysis, quality scoring, domain and social media availability, and trademark checks. Use when naming products, startups, apps, or brands, evaluating name candidates, or checking domain availability.
Agent team role for project delivery management using PRINCE2 principles. Use when the user asks to plan project stages, manage risks, track progress, write highlight reports, handle exceptions, create work packages, or ensure continued business justification. Owns the "when" and "how much" — controls stages, timelines, resources, and escalates when tolerances are exceeded.
Expert backend architecture and project structure for scalable, secure, maintainable applications. Inspects the existing stack before writing code, prefers feature-based modules, and adapts to Express, NestJS, Fastify, Django, Rails, Go, and other backends. Use when designing backend structure, reviewing architecture, refactoring modules, or building production-grade backend features.
In the AI assistant in your IDE, help users directly complete ProtoLink project preview, iteration preview, viewing local iterations, creating/updating/publishing iterations, getting online links, publish configuration diagnostics, and installation and updates of the ProtoLink CLI / Skill suite; supports natural phrasings such as "open the preview of the current project", "see what iterations there are", "publish this iteration and give me the link", "see why it can't be published yet", "install the ProtoLink service", "install ProtoLink CLI", and "update ProtoLink Skill"
Proxmox VE virtualization platform reference for VM/LXC management, clustering, storage, and networking. Includes Terraform and Ansible integration patterns. Use when working with Proxmox configurations, CLI commands, troubleshooting VMs/containers, or planning resource allocation. Triggers: proxmox, qemu, kvm, lxc, pve, vm, container, cluster, vzdump, qm, pct.
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNorm lookup and cross-mapping). Use this skill whenever the user mentions PyHealth, MIMIC, eICU, OMOP, EHR modeling, clinical prediction, drug recommendation, sleep staging, medical code mapping, ICD/ATC codes, or any healthcare ML pipeline that fits the dataset → task → model → trainer → metrics pattern, even if "PyHealth" isn't named explicitly.
Python performance profiling with cProfile, tracemalloc, and line_profiler. Use for identifying bottlenecks and memory issues. USE WHEN: user mentions "Python profiling", "cProfile", "memory profiling", asks about "Python performance", "tracemalloc", "line_profiler", "py-spy", "Python optimization", "Python memory leak" DO NOT USE FOR: Java/Node.js profiling - use respective skills instead
Python typing best practices: annotate public signatures, use modern syntax (`X | None`, PEP 695 generics, `type` aliases), make absence explicit and narrow types, prefer `Protocol` over unchecked duck typing, avoid `Any`, and validate with a strict type checker (pyrefly, ty, `mypy --strict` or pyright). Consult whenever you add or modify type annotations in Python, design a typed API/library, define generics/protocols/TypedDict, configure pyrefly/ty/mypy/pyright, or fix type checker errors — even if the user doesn't explicitly say “typing”.
Activates on any Python task involving *.py files, uv, ruff, ty, pytest, or pyproject.toml — loads the shared Python 3.11+ standards and routes the task to the specialist skill that applies them: TDD, CLI, web, data, async, typing, packaging, publishing, documentation sites, test design, test-failure analysis, or stdlib-only constrained environments.
Formal Quality Assurance Checklist before every Merge/Deploy. 6-phase validation with Build Verification, Test Suite, No-Touch Zones, Region Check, Security Review, and QA Report generation. Activate on "merge", "deploy", "release", "production", or /qa command.
If the user asks to explore, analyze, query, chart, dashboard, or govern (master items, business glossary, data products) a Qlik Sense app or Qlik Cloud analytics content via the Qlik MCP server — THEN invoke this skill. This covers requests like "what's in this Qlik app", "chart X by Y in [app]", "build a sheet for...", "create a reusable measure for...", "what does [glossary term] mean", "is this dataset trustworthy/fresh", or any question that requires calling qlik_* MCP tools. DO NOT invoke for SQL warehouse questions, DW/BI-tool-agnostic data modelling, or requests with no Qlik MCP tool involved.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.